© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12177
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to JavaScript and AngularJS code in HTML documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, database, or command-line related syntax

    np_acts-logits-general · gemini-2.0-flash

    for loop syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Geduld
    -0.35
     też
    -0.34
     hiszen
    -0.33
     sienta
    -0.33
     nød
    -0.33
     Gebet
    -0.33
     relatifs
    -0.31
    éről
    -0.31
     rozwo
    -0.30
     natten
    -0.30
    POSITIVE LOGITS
     للاسماء
    0.73
     للمعارف
    0.66
    
    0.64
    ๥
    0.62
    姎
    0.61
     ſondern
    0.60
    ꪼ
    0.60
    
    0.60
    <unused94>
    0.59
    
    0.59
    Activations Density 1.096%

    No Known Activations